清理已删除的测试文件，准备云端部署

scheduler.py

@@ -12,11 +12,12 @@ r"""
   3. Linux cron（每天早上 8:00）:
      0 8 * * * cd /path/to/ztb && python scheduler.py >> logs/cron.log 2>&1
 """
+import glob
 import logging
 import sys
 import os
 import traceback
-from datetime import datetime
+from datetime import datetime, timedelta
 
 # 确保项目根目录在 sys.path 中
 sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
@@ -59,18 +60,40 @@ DAILY_TASKS = [
         "process": True,
         "upload": True,
     },
-    # 台州 - 工程建设 - 招标文件公示
+    # 台州 - 工程建设 - 招标计划公示
     {
         "site": "taizhou",
         "max_pages": 100,
         "category": "工程建设",
-        "notice_type": "招标文件公示",
+        "notice_type": "招标计划公示",
         "process": True,
         "upload": True,
     },
 ]
 
 
+# 数据文件保留天数
+KEEP_DAYS = 30
+
+
+def cleanup_old_files(directory: str, keep_days: int = KEEP_DAYS):
+    """清理超过 keep_days 天的 CSV 和 JSON 文件"""
+    if not os.path.isdir(directory):
+        return
+    cutoff = datetime.now() - timedelta(days=keep_days)
+    removed = 0
+    for pattern in ("*.csv", "*.json"):
+        for filepath in glob.glob(os.path.join(directory, pattern)):
+            if os.path.getmtime(filepath) < cutoff.timestamp():
+                try:
+                    os.remove(filepath)
+                    removed += 1
+                except OSError:
+                    pass
+    if removed:
+        logger.info(f"清理 {directory} 中 {removed} 个超过 {keep_days} 天的文件")
+
+
 def run_task(task: dict, date_filter: str = "yesterday") -> int:
     """执行单个爬取任务，返回采集条数"""
     site = task["site"]
@@ -137,6 +160,9 @@ def run_daily():
             logger.debug(traceback.format_exc())
             errors.append(desc)
 
+    # 清理过期数据文件
+    cleanup_old_files(DATA_DIR)
+
     elapsed = (datetime.now() - start).total_seconds()
     logger.info("=" * 40)
     logger.info(f"定时任务完成: 共 {total} 条, 耗时 {elapsed:.0f}s")